Abstract
The paper presents a method which uses the activity patterns of simulated neural networks for classification/identification and for combining classification concepts by a chunking process. Furthermore it will be shown that if a neighborhood function similar to the Sinc function is used, the activity of neurons or neuron clusters can be used to compute — based on physical principles like superposition and interference of waves — with activity patterns.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Benesch, H.: Der Ursprung des Geistes, dtv, 1972
Aizenberg, I. N.: Neural Networks Based on Multi-valued and Universal Binary Neurons: Theory, Application to Image Processing and Recognition, Computational Intelligence, in Lecture Notes in Computer Science, 1625 pp,. 306–317, Springer, Dortmund, 1999
Reuter, M.: About the Quantisation of the Neural Nets, in: Lecture Notes in Computer Science, pp. 530–542, Springer, Dortmund, 1999
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Reuter, M. (2001). Computing with Activity Patterns. In: Reusch, B. (eds) Computational Intelligence. Theory and Applications. Fuzzy Days 2001. Lecture Notes in Computer Science, vol 2206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45493-4_22
Download citation
DOI: https://doi.org/10.1007/3-540-45493-4_22
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42732-2
Online ISBN: 978-3-540-45493-9
eBook Packages: Springer Book Archive